This guide introduces Computer Vision, a branch of Artificial Intelligence that enables machines to interpret and analyse visual data using Deep Learning, particularly Convolutional Neural Networks. It outlines key functions such as object detection, image segmentation, and motion analysis, along with challenges like data bias, occlusion, and ethical concerns. Focusing on the library and cultural heritage sectors, the guide explores how Computer Vision enhances image classification, metadata creation, visual search, text recognition (OCR/HTR), and accessibility. Case studies—from tools like Sheeko, imgs.ai, and JADIS—demonstrate its value in enriching collections and improving user access.
